Publicaties
Gekozen filters:
Gekozen filters:
Task-free continual learning KU Leuven
Exploring the challenges towards lifelong fact learning KU Leuven
© 2019, Springer Nature Switzerland AG. So far life-long learning (LLL) has been studied in relatively small-scale and relatively artificial setups. Here, we introduce a new large-scale alternative. What makes the proposed setup more natural and closer to human-like visual systems is threefold: First, we focus on concepts (or facts, as we call them) of varying complexity, ranging from single objects to more complex structures such as objects ...
Selfless sequential learning KU Leuven
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks KU Leuven
Visual Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations. We interpret the model through average visualizations of this ...